Robot Cleaning Path Planning Using Maximum Envelope Regions
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing full-coverage path planning methods for cleaning robots suffer from low efficiency, weak adaptability, and limited application scenarios due to manual teaching methods leading to excessive or missed cleaning, and environmental uncertainty in boundary-based methods.
Innovation Solution
A method and apparatus that involve acquiring a training trajectory and environment map, generating a maximum envelope region for tasks, and controlling the robot to traverse this region until completion, using grid expansion and path planning to ensure efficient and stable task execution in various environments.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If manual teaching method is used to determine robot path, then adaptability to complex structured scenarios is improved, but cleaning efficiency deteriorates due to path duplication and missed areas
Solution Approach 1:
The system performs preliminary actions by first teaching only the boundary path and key feature points rather than the complete cleaning trajectory. The robot then autonomously generates the full cleaning path based on these preliminary teachings, avoiding the need to manually teach every path point while still achieving adaptability to complex scenarios.
Solution Approach 2:
The robot performs self-service by autonomously generating its own cleaning path based on the taught boundary and feature points. The path planning algorithm automatically calculates the optimal cleaning trajectory without human intervention, eliminating path duplication and missed areas while maintaining adaptability.
2Productivity
If boundary full coverage method is used for autonomous cleaning, then cleaning efficiency is improved, but adaptability to complex structured scenarios deteriorates
Solution Approach 1:
The system applies local quality by treating different regions of the cleaning area differently. The boundary and key feature points are manually taught with high precision, while the interior cleaning path is autonomously generated. This allows the robot to handle complex boundary structures accurately while efficiently planning the interior cleaning path.
Solution Approach 2:
The system implements dynamics by making the path generation process adaptive rather than static. The robot dynamically adjusts the cleaning path based on the taught boundary and feature points, allowing it to adapt to various complex structured scenarios while maintaining efficient autonomous operation.
3Adaptability or versatility
If manual teaching of complete path is performed, then adaptability to complex scenarios is improved, but time consumption and operational complexity increase
Solution Approach 1:
The system extracts only the essential elements (boundary path and key feature points) from the complete cleaning trajectory for manual teaching. The non-essential interior path points are automatically generated by the robot's path planning algorithm, significantly reducing the time and effort required for manual teaching while maintaining adaptability to complex scenarios.
4Adaptability or versatility
If manual teaching method is used, then path can adapt to complex structures, but operational complexity and error potential increase
Solution Approach 1:
The system performs preliminary action by teaching only the boundary and key feature points before autonomous operation. This preliminary setup captures the essential structural information needed for adaptability, while the subsequent autonomous path generation eliminates the complexity of manually configuring every path point.
Solution Approach 2:
The robot performs self-service by autonomously generating the complete cleaning path based on the taught boundary and feature points. This self-path-planning capability eliminates manual configuration errors and reduces operational complexity while maintaining adaptability to complex structured scenarios.
Data Source
Figure 1~2
Figure 3~4(d)
Figure 5~6
AI summary
The present application discloses a robot task execution method, apparatus, robot and storage medium. The method comprises: acquiring a training trajectory and an environment map in a training mode; generating a target region for tasks to be performed by a robot based on the environment map and the training trajectory, wherein the target region is a maximum envelope region in which the robot can complete tasks autonomously; controlling the robot to traverse the target region until the robot completes the tasks to be performed. By adopting the above technical solution, the robot can perform tasks stably and efficiently in various environmental regions, thereby being able to be applied to various application scenarios.